Zhipu AI model product
GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.
Updated Aug 10, 2026. Default version: GLM-4.7
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version GLM-4.7.
| Tau-bench | 0.9 | 2 | 6 | 80.0% | C | |
| BrowseComp-zh | 0.7 | 5 | 13 | 66.7% | C | |
| LiveCodeBench v6 | 0.8 | 10 | 53 | 82.7% | C | |
| IMO-AnswerBench | 0.8 | 12 | 19 | 38.9% | C | |
| Terminal-Bench | 0.3 | 16 | 25 | 37.5% | C | |
| AIME 2025 | 1.0 | 21 | 114 | 82.3% | C | |
| SWE-bench Multilingual | 0.7 | 23 | 34 | 33.3% | C | |
| MMLU-Pro | 0.8 | 26 | 129 | 80.5% | C | |
| Humanity's Last Exam | 0.4 | 30 | 92 | 68.1% | C | |
| SWE-Bench Verified | 0.7 | 39 | 104 | 63.1% | C | |
| BrowseComp | 0.5 | 40 | 58 | 31.6% | C | |
| Terminal-Bench 2.0 | 0.4 | 44 | 49 | 10.4% | C | |
| GPQA | 0.9 | 48 | 233 | 79.7% | C |
Preference and agent-evaluation signals from published Arena datasets.
| text | industry medicine and healthcare | 36 | 1463.0 | 813 | N/A | |
| text style control | industry medicine and healthcare | 41 | 1480.8 | 813 | N/A | |
| text | korean | 43 | 1406.1 | 159 | N/A | |
| text | english | 45 | 1453.6 | 5,564 | N/A | |
| webdev | webdev-html | 45 | 1445.7 | 3,689 | N/A | |
| webdev | webdev-react | 49 | 1424.4 | 99 | N/A | |
| webdev | overall | 51 | 1433.5 | 3,796 | N/A | |
| webdev | webdev | 51 | 1433.5 | 3,796 | N/A | |
| text | chinese | 54 | 1483.9 | 685 | N/A | |
| text | industry life and physical and social science | 54 | 1455.3 | 2,080 | N/A | |
| text style control | korean | 54 | 1406.8 | 159 | N/A | |
| text | multi turn | 56 | 1448.0 | 1,920 | N/A | |
| text factuality | english | 57 | 1457.3 | 5,305 | N/A | |
| text | hard prompts english | 60 | 1452.1 | 3,087 | N/A | |
| text | industry legal and government | 60 | 1444.8 | 954 | N/A | |
| text style control | english | 60 | 1462.2 | 5,564 | N/A | |
| text style control | industry life and physical and social science | 60 | 1470.6 | 2,080 | N/A | |
| text factuality | multi turn | 61 | 1456.3 | 1,331 | N/A | |
| text factuality | exclude ties | 62 | 1446.1 | 8,034 | N/A | |
| text style control | multi turn | 64 | 1459.2 | 1,920 | N/A | |
| text | industry business and management and financial operations | 65 | 1428.4 | 2,241 | N/A | |
| text factuality | industry entertainment and sports and media | 65 | 1412.0 | 1,610 | N/A | |
| text style control | chinese | 65 | 1486.1 | 685 | N/A | |
| text style control | hard prompts english | 66 | 1472.9 | 3,087 | N/A | |
| text | exclude ties | 67 | 1431.5 | 8,362 | N/A | |
| text | russian | 67 | 1427.2 | 1,354 | N/A | |
| text factuality | creative writing | 67 | 1414.7 | 1,242 | N/A | |
| text style control | longer query | 67 | 1451.4 | 3,079 | N/A | |
| text | hard prompts | 68 | 1443.8 | 6,590 | N/A | |
| text | coding | 69 | 1455.8 | 2,410 | N/A | |
| text | longer query | 69 | 1433.6 | 3,079 | N/A | |
| text factuality | industry business and management and financial operations | 69 | 1443.7 | 1,560 | N/A | |
| text factuality | overall | 70 | 1443.5 | 11,661 | N/A | |
| text | overall | 71 | 1435.5 | 12,077 | N/A | |
| text factuality | industry writing and literature and language | 71 | 1421.7 | 1,875 | N/A | |
| text style control | hard prompts | 71 | 1462.7 | 6,590 | N/A | |
| text | industry writing and literature and language | 72 | 1411.4 | 2,755 | N/A | |
| text factuality | non english | 72 | 1427.8 | 6,268 | N/A | |
| text style control | industry legal and government | 72 | 1454.1 | 954 | N/A | |
| text style control | exclude ties | 73 | 1441.4 | 8,362 | N/A | |
| text | industry entertainment and sports and media | 74 | 1402.2 | 2,381 | N/A | |
| text factuality | longer query | 74 | 1448.6 | 2,249 | N/A | |
| text style control | overall | 74 | 1441.8 | 12,077 | N/A | |
| text | polish | 75 | 1424.7 | 422 | N/A | |
| text factuality | hard prompts | 75 | 1462.8 | 6,302 | N/A | |
| text style control | industry business and management and financial operations | 75 | 1441.7 | 2,241 | N/A | |
| text | industry software and it services | 76 | 1452.9 | 4,100 | N/A | |
| text factuality | industry life and physical and social science | 76 | 1459.6 | 1,409 | N/A | |
| text style control | industry software and it services | 77 | 1474.3 | 4,100 | N/A | |
| text | non english | 78 | 1416.0 | 6,513 | N/A | |
| text factuality | hard prompts english | 78 | 1467.8 | 2,255 | N/A | |
| text style control | instruction following | 78 | 1427.7 | 3,208 | N/A | |
| text style control | polish | 78 | 1426.2 | 422 | N/A | |
| text style control | industry entertainment and sports and media | 79 | 1405.9 | 2,381 | N/A | |
| text style control | industry writing and literature and language | 79 | 1416.6 | 2,755 | N/A | |
| text | instruction following | 80 | 1413.3 | 3,208 | N/A | |
| text factuality | russian | 81 | 1427.4 | 881 | N/A | |
| text style control | coding | 81 | 1485.5 | 2,410 | N/A | |
| text | creative writing | 82 | 1402.0 | 1,912 | N/A | |
| text | german | 82 | 1419.6 | 219 | N/A | |
| text style control | russian | 82 | 1432.2 | 1,354 | N/A | |
| text style control | creative writing | 83 | 1405.1 | 1,912 | N/A | |
| text factuality | coding | 84 | 1480.3 | 1,690 | N/A | |
| text style control | spanish | 85 | 1423.2 | 314 | N/A | |
| text factuality | industry software and it services | 86 | 1470.0 | 3,375 | N/A | |
| text factuality | instruction following | 86 | 1423.3 | 2,341 | N/A | |
| text style control | non english | 86 | 1420.1 | 6,513 | N/A | |
| text style control | german | 91 | 1421.1 | 219 | N/A | |
| text style control | math | 91 | 1427.1 | 695 | N/A | |
| text style control | french | 93 | 1443.7 | 267 | N/A | |
| text | french | 95 | 1427.8 | 267 | N/A | |
| text | spanish | 95 | 1416.5 | 314 | N/A | |
| text | math | 96 | 1422.4 | 695 | N/A | |
| text style control | expert | 104 | 1443.5 | 716 | N/A | |
| text | expert | 112 | 1418.1 | 716 | N/A | |
| text style control | industry mathematical | 113 | 1419.7 | 538 | N/A | |
| text | industry mathematical | 121 | 1410.3 | 538 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| Zhipu AI Coding Plan | glm-4.7 | global | N/A | N/A | 204.8K | |
| Alibaba Coding Plan (China) | glm-4.7 | global | N/A | N/A | 202.8K | |
| Alibaba Coding Plan | glm-4.7 | global | N/A | N/A | 202.8K | |
| KUAE Cloud Coding Plan | GLM-4.7 | global | N/A | N/A | 204.8K | |
| Z.AI Coding Plan | glm-4.7 | global | N/A | N/A | 204.8K | |
| CrofAI | glm-4.7 | global | $0.25 | $1.1 | 202.8K | |
| 302.AI | glm-4.7 | global | $0.286 | $1.14 | 204.8K | |
| LLM Gateway | glm-4.7 | global | $0.38 | $1.98 | 204.8K | |
| DInference | glm-4.7 | global | $0.45 | $1.65 | 200K | |
| OpenCode Zen | glm-4.7 | global | $0.60 | $2.2 | 204.8K | |
| Z.AI | glm-4.7 | global | $0.60 | $2.2 | 204.8K | |
| Cortecs | glm-4.7 | global | $0.78 | $2.79 | 202.8K | |
| Moark | GLM-4.7 | global | $3.5 | $14 | 204.8K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| GLM-4.7 | 66.2 | 358B | 204.8K | 131.1K | Yes | MIT |
A concise description based on the published model registry.
GLM 4.7 is a coding‑centric model that thinks before acting, preserves its reasoning across turns, and lets you control thinking per request for speed or accuracy. It upgrades agentic workflows with stronger multi‑step tool use, better terminal and multilingual coding, and a noticeable jump in UI output quality for modern, clean webpages and slides. You can use it in popular coding agents, call it via the Z.ai API, and even run it locally with public weights on HuggingFace and ModelScope using vLLM or SGLang.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about GLM 4.7.
GLM 4.7's default version was released on Dec 22, 2025.
No official standard PAYG price is currently available for GLM 4.7. The lowest tracked third-party offer starts at $0.25 input and $1.1 output via CrofAI.
GLM 4.7 is published under Zhipu AI in the model registry.
The default version has a 204.8K token context window.
Yes. The default version is marked as open weight under MIT.
13 published provider offerings are linked to the default version.
Nearby ranked alternatives include MiMo V2.5 Pro, Gemma 4 26B A4B, Grok 4 Fast.